Search

Abstract Sex and gender differences play a crucial role in health and disease outcomes. This study used data from the National Health and Nutrition Examination Survey to explore how environmental exposures affect health-related traits differently in males and females. We utilized a sex-stratified phenomic environment-wide association study (PheEWAS), which allowed the identification of associations across a wide range of phenotypes and environmental exposures. We examined associations between 272 environmental exposures, including smoking-related exposures such as cotinine levels and smoking habits, and 58 clinically relevant blood phenotypes, such as serum albumin and homocysteine levels. Our analysis identified 119 sex-specific associations. For example, smoking-related exposures had a stronger impact on increasing homocysteine, hemoglobin, and hematocrit levels in females while reducing serum albumin and bilirubin levels and increasing c-reactive protein levels more significantly in males. These findings suggest mechanisms by which smoking exposure may pose higher cardiovascular risks and greater induced hypoxia for women, and greater inflammatory and immune responses in men. The results highlight the importance of considering sex differences in biomedical research. Understanding these differences can help develop more personalized and effective health interventions and improve clinical outcomes for both men and women.

Objective Recent studies have reported that gout is associated with a risk of cardiovascular disease (CVD) later in life. However, the predictive value of genetic predisposition to gout combined with lifestyle habits for CVD risk remains unclear. This study aimed to examine the association between genetic predisposition to gout and lifestyle habits and the risk of developing CVD in two diverse prospective cohorts from different ancestries.Methods A total of 224 689 participants of European descent from the UK Biobank and 50 364 participants of East Asian descent from the Korean Genome and Epidemiology Study were included. The genetic risk for gout was assessed using a polygenic risk score (PRS) derived from a meta-genome-wide association study (n=444 533). The incident CVD risk was evaluated according to genetic risk, lifestyle and metabolic syndrome (MetS).Results Individuals at high genetic risk for gout had a higher risk of incident CVD than those with low genetic risk across ancestry. Notably, a reduction in CVD risk by up to 62% (HR 0.38; 95% CI 0.31 to 0.46; p

Abstract Background Supervised machine learning models have been widely used to predict and get insight into diseases by classifying patients based on personal health records. However, a class imbalance is an obstacle that disrupts the training of the models. In this study, we aimed to address class imbalance with a conditional normalizing flow model, one of the deep-learning-based semi-supervised models for anomaly detection. It is the first introduction of the normalizing flow algorithm for tabular biomedical data. Methods We collected personal health records from South Korean citizens (n = 706), featuring genetic data obtained from direct-to-customer service (microarray chip), medical health check-ups, and lifestyle log data. Based on the health check-up data, six chronic diseases were labeled (obesity, diabetes, hypertriglyceridemia, dyslipidemia, liver dysfunction, and hypertension). After preprocessing, supervised classification models and semi-supervised anomaly detection models, including conditional normalizing flow, were evaluated for the classification of diabetes, which had extreme target imbalance (about 2%), based on AUROC and AUPRC. In addition, we evaluated their performance under the assumption of insufficient collection for patients with other chronic diseases by undersampling disease-affected samples. Results While LightGBM (the best-performing model among supervised classification models) showed AUPRC 0.16 and AUROC 0.82, conditional normalizing flow achieved AUPRC 0.34 and AUROC 0.83 during fifty evaluations of the classification of diabetes, whose base rate was very low, at 0.02. Moreover, conditional normalizing flow performed better than the supervised model under a few disease-affected data numbers for the other five chronic diseases – obesity, hypertriglyceridemia, dyslipidemia, liver dysfunction, and hypertension. For example, while LightGBM performed AUPRC 0.20 and AUROC 0.75, conditional normalizing flow showed AUPRC 0.30 and AUROC 0.74 when predicting obesity, while undersampling disease-affected samples (positive undersampling) lowered the base rate to 0.02. Conclusions Our research suggests the utility of conditional normalizing flow, particularly when the available cases are limited, for predicting chronic diseases using personal health records. This approach offers an effective solution to deal with sparse data and extreme class imbalances commonly encountered in the biomedical context.

Abstract Background Cardiometabolic disorders pose significant health risks globally. Metabolic syndrome, characterized by a cluster of potentially reversible metabolic abnormalities, is a known risk factor for these disorders. Early detection and intervention for individuals with metabolic abnormalities can help mitigate the risk of developing more serious cardiometabolic conditions. This study aimed to develop an image-derived phenotype (IDP) for metabolic abnormality from unenhanced abdominal computed tomography (CT) scans using deep learning. We used this IDP to classify individuals with metabolic syndrome and predict future occurrence of cardiometabolic disorders. Methods A multi-stage deep learning approach was used to extract the IDP from the liver region of unenhanced abdominal CT scans. In a cohort of over 2,000 individuals the IDP was used to classify individuals with metabolic syndrome. In a subset of over 1,300 individuals, the IDP was used to predict future occurrence of hypertension, type II diabetes, and fatty liver disease. Results For metabolic syndrome (MetS) classification, we compared the performance of the proposed IDP to liver attenuation and visceral adipose tissue area (VAT). The proposed IDP showed the strongest performance (AUC 0.82) compared to attenuation (AUC 0.70) and VAT (AUC 0.80). For disease prediction, we compared the performance of the IDP to baseline MetS diagnosis. The models including the IDP outperformed MetS for type II diabetes (AUCs 0.91 and 0.90) and fatty liver disease (AUCs 0.67 and 0.62) prediction and performed comparably for hypertension prediction (AUCs of 0.77). Conclusions This study demonstrated the superior performance of a deep learning IDP compared to traditional radiomic features to classify individuals with metabolic syndrome. Additionally, the IDP outperformed the clinical definition of metabolic syndrome in predicting future morbidities. Our findings underscore the utility of data-driven imaging phenotypes as valuable tools in the assessment and management of metabolic syndrome and cardiometabolic disorders.

Abstract Background Glaucoma is a leading cause of worldwide irreversible blindness. Considerable uncertainty remains regarding the association between a variety of phenotypes and the genetic risk of glaucoma, as well as the impact they exert on the glaucoma development. Methods We investigated the associations of genetic liability for primary open angle glaucoma (POAG) with a wide range of potential risk factors and to assess its impact on the risk of incident glaucoma. The phenome-wide association study (PheWAS) approach was applied to determine the association of POAG polygenic risk score (PRS) with a wide range of phenotypes in 377, 852 participants from the UK Biobank study and 43,623 participants from the Penn Medicine Biobank study, all of European ancestry. Participants were stratified into four risk tiers: low, intermediate, high, and very high-risk. Cox proportional hazard models assessed the relationship of POAG PRS and ocular factors with new glaucoma events. Results In both discovery and replication set in the PheWAS, a higher genetic predisposition to POAG was specifically correlated with ocular disease phenotypes. The POAG PRS exhibited correlations with low corneal hysteresis, refractive error, and ocular hypertension, demonstrating a strong association with the onset of glaucoma. Individuals carrying a high genetic burden exhibited a 9.20-fold, 11.88-fold, and 28.85-fold increase in glaucoma incidence when associated with low corneal hysteresis, high myopia, and elevated intraocular pressure, respectively. Conclusion Genetic susceptibility to POAG primarily influences ocular conditions, with limited systemic associations. Notably, the baseline polygenic risk for POAG robustly associates with new glaucoma events, revealing a large combined effect of genetic and ocular risk factors on glaucoma incidents.

Abstract Background Previous studies have shown that lifestyle/environmental factors could accelerate the development of age-related hearing loss (ARHL). However, there has not yet been a study investigating the joint association among genetics, lifestyle/environmental factors, and adherence to healthy lifestyle for risk of ARHL. We aimed to assess the association between ARHL genetic variants, lifestyle/environmental factors, and adherence to healthy lifestyle as pertains to risk of ARHL. Methods This case–control study included 376,464 European individuals aged 40 to 69 years, enrolled between 2006 and 2010 in the UK Biobank (UKBB). As a replication set, we also included a total of 26,523 individuals considered of European ancestry and 9834 individuals considered of African-American ancestry through the Penn Medicine Biobank (PMBB). The polygenic risk score (PRS) for ARHL was derived from a sensorineural hearing loss genome-wide association study from the FinnGen Consortium and categorized as low, intermediate, high, and very high. We selected lifestyle/environmental factors that have been previously studied in association with hearing loss. A composite healthy lifestyle score was determined using seven selected lifestyle behaviors and one environmental factor. Results Of the 376,464 participants, 87,066 (23.1%) cases belonged to the ARHL group, and 289,398 (76.9%) individuals comprised the control group in the UKBB. A very high PRS for ARHL had a 49% higher risk of ARHL than those with low PRS (adjusted OR, 1.49; 95% CI, 1.36–1.62; P

Abstract Background Numerous observational studies have highlighted associations of genetic predisposition of head and neck squamous cell carcinoma (HNSCC) with diverse risk factors, but these findings are constrained by design limitations of observational studies. In this study, we utilized a phenome-wide association study (PheWAS) approach, incorporating a polygenic risk score (PRS) derived from a wide array of genomic variants, to systematically investigate phenotypes associated with genetic predisposition to HNSCC. Furthermore, we validated our findings across heterogeneous cohorts, enhancing the robustness and generalizability of our results. Methods We derived PRSs for HNSCC and its subgroups, oropharyngeal cancer and oral cancer, using large-scale genome-wide association study summary statistics from the Genetic Associations and Mechanisms in Oncology Network. We conducted a comprehensive investigation, leveraging genotyping data and electronic health records from 308,492 individuals in the UK Biobank and 38,401 individuals in the Penn Medicine Biobank (PMBB), and subsequently performed PheWAS to elucidate the associations between PRS and a wide spectrum of phenotypes. Results We revealed the HNSCC PRS showed significant association with phenotypes related to tobacco use disorder (OR, 1.06; 95% CI, 1.05–1.08; P = 3.50 × 10−15), alcoholism (OR, 1.06; 95% CI, 1.04–1.09; P = 6.14 × 10-9), alcohol-related disorders (OR, 1.08; 95% CI, 1.05–1.11; P = 1.09 × 10−8), emphysema (OR, 1.11; 95% CI, 1.06–1.16; P = 5.48 × 10−6), chronic airway obstruction (OR, 1.05; 95% CI, 1.03–1.07; P = 2.64 × 10−5), and cancer of bronchus (OR, 1.08; 95% CI, 1.04–1.13; P = 4.68 × 10−5). These findings were replicated in the PMBB cohort, and sensitivity analyses, including the exclusion of HNSCC cases and the major histocompatibility complex locus, confirmed the robustness of these associations. Additionally, we identified significant associations between HNSCC PRS and lifestyle factors related to smoking and alcohol consumption. Conclusions The study demonstrated the potential of PRS-based PheWAS in revealing associations between genetic risk factors for HNSCC and various phenotypic traits. The findings emphasized the importance of considering genetic susceptibility in understanding HNSCC and highlighted shared genetic bases between HNSCC and other health conditions and lifestyles.

Abstract We investigated the effects of gender and lifestyle on the association between frequency of depressive symptoms and CVD risk. The UK Biobank is a national prospective cohort study that recruited 502,505 participants aged 40–69 years between 2006 and 2010. Participants without CVD were classified as having low, moderate, high, or very high frequency of depressive symptoms according to the number of days they felt depressed in a 2-week period. UKBB data include self-reported questionnaires covering lifestyle behaviors such as smoking, physical activity, eating habits, and sleep duration. The primary outcomes included incident CVD including coronary artery disease, ischemic stroke, hemorrhagic stroke, peripheral artery disease, atrial fibrillation/flutter, and heart failure. Cox proportional hazard models were used to evaluate the effects of gender and lifestyle on the association of frequency of depressive symptoms and CVD risk. During a median follow-up of 8.9 years, 27,394 (6.3%) developed CVD. The frequency of depressive symptoms increased the risk of CVD according to low, moderate, high, and very high frequency of depressive symptoms (P for trend

Abstract Background Computational drug repurposing is crucial for identifying candidate therapeutic medications to address the urgent need for developing treatments for newly emerging infectious diseases. The recent COVID-19 pandemic has taught us the importance of rapidly discovering candidate drugs and providing them to medical and pharmaceutical experts for further investigation. Network-based approaches can provide repurposable drugs quickly by leveraging comprehensive relationships among biological components. However, in a case of newly emerging disease, applying a repurposing methods with only pre-existing knowledge networks may prove inadequate due to the insufficiency of information flow caused by the novel nature of the disease. Methods We proposed a network-based complementary linkage method for drug repurposing to solve the lack of incoming new disease-specific information in knowledge networks. We simulate our method under the controlled repurposing scenario that we faced in the early stage of the COVID-19 pandemic. First, the disease-gene-drug multi-layered network was constructed as the backbone network by fusing comprehensive knowledge database. Then, complementary information for COVID-19, containing data on 18 comorbid diseases and 17 relevant proteins, was collected from publications or preprint servers as of May 2020. We estimated connections between the novel COVID-19 node and the backbone network to construct a complemented network. Network-based drug scoring for COVID-19 was performed by applying graph-based semi-supervised learning, and the resulting scores were used to validate prioritized drugs for population-scale electronic health records-based medication analyses. Results The backbone networks consisted of 591 diseases, 26,681 proteins, and 2,173 drug nodes based on pre-pandemic knowledge. After incorporating the 35 entities comprised of complemented information into the backbone network, drug scoring screened top 30 potential repurposable drugs for COVID-19. The prioritized drugs were subsequently analyzed in electronic health records obtained from patients in the Penn Medicine COVID-19 Registry as of October 2021 and 8 of these were found to be statistically associated with a COVID-19 phenotype. Conclusion We found that 8 of the 30 drugs identified by graph-based scoring on complemented networks as potential candidates for COVID-19 repurposing were additionally supported by real-world patient data in follow-up analyses. These results show that our network-based complementary linkage method and drug scoring algorithm are promising strategies for identifying candidate repurposable drugs when new emerging disease outbreaks.

IntroductionStratification of Alzheimer’s disease (AD) patients into risk subgroups using Polygenic Risk Scores (PRS) presents novel opportunities for the development of clinical trials and disease-modifying therapies. However, the heterogeneous nature of AD continues to pose significant challenges for the clinical broadscale use of PRS. PRS remains unfit in demonstrating sufficient accuracy in risk prediction, particularly for individuals with mild cognitive impairment (MCI), and in allowing feasible interpretation of specific genes or SNPs contributing to disease risk. We propose adORS, a novel oligogenic risk score for AD, to better predict risk of disease by using an optimized list of relevant genetic risk factors.MethodsUsing whole genome sequencing data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort (n = 1,545), we selected 20 genes that exhibited the strongest correlations with FDG-PET and AV45-PET, recognized neuroimaging biomarkers that detect functional brain changes in AD. This subset of genes was incorporated into adORS to assess, in comparison to PRS, the prediction accuracy of CN vs. AD classification and MCI conversion prediction, risk stratification of the ADNI cohort, and interpretability of the genetic information included in the scores.ResultsadORS improved AUC scores over PRS in both CN vs. AD classification and MCI conversion prediction. The oligogenic model also refined risk-based stratification, even without the assistance of APOE, thus reflecting the true prevalence rate of the ADNI cohort compared to PRS. Interpretation analysis shows that genes included in adORS, such as ATF6, EFCAB11, ING5, SIK3, and CD46, have been observed in similar neurodegenerative disorders and/or are supported by AD-related literature.DiscussionCompared to conventional PRS, adORS may prove to be a more appropriate choice of differentiating patients into high or low genetic risk of AD in clinical studies or settings. Additionally, the ability to interpret specific genetic information allows the focus to be shifted from general relative risk based on a given population to the information that adORS can provide for a single individual, thus permitting the possibility of personalized treatments for AD.

Abstract Background A significant proportion of colorectal cancer (CRC) patients suffer from early recurrence and progression after surgical treatment. Although the gut microbiota is considered as a key player in the initiation and progression of CRC, most prospective studies have been focused on a particular pathobionts such as Fusobacterium nucleatum. Here, we aimed to identify novel prognostic bacteria for CRC by examining the preoperative gut microbiota through 16S ribosomal RNA gene sequencing. Results We collected stool samples from 333 patients with primary CRC within 2 weeks before surgery and followed up the patients for a median of 27.6 months for progression and 43.6 months for survival. The sequence and prognosis data were assessed using the log-rank test and multivariate Cox proportional hazard analysis. The gut microbiota was associated with the clinical outcomes of CRC patients (P progress = 0.011, P decease = 0.007). In particular, the high abundance of Prevotella, a representative genus of human enterotypes, indicated lower risks of CRC progression (P = 0.026) and decease (P = 0.0056), while the occurrence of Alistipes assigned to Bacteroides sp., Pyramidobacter piscolens, Dialister invisus, and Fusobacterium nucleatum indicated a high risk of progression. A microbiota-derived hazard score considering the five prognostic bacteria accurately predicted CRC progression in 1000 random subsamples; it outperformed widely accepted clinical biomarkers such as carcinoembryonic antigen and lymphatic invasion, after adjustment for the clinicopathological stage (adjusted HR 2.07 [95% CI, 1.61–2.64], P = 7.8e−9, C-index = 0.78). PICRUSt2 suggested that microbial pathways pertaining to thiamine salvage and L-histidine degradation underlie the different prognoses. Conclusions The enterotypical genus Prevotella was demonstrated to be useful in improving CRC prognosis, and combined with the four pathobionts, our hazard score based on the gut microbiota should provide an important asset in predicting medical outcomes for CRC patients. Video Abstract

Abstract Background Previous studies showed that gestational diabetes mellitus (GDM) can be a risk factor for subsequent atherosclerotic cardiovascular disease. However, there is a paucity of information regarding diverse cardiovascular outcomes in elderly women after GDM. In the current study, we examined whether women with a history of GDM have an increased risk for long-term overall cardiovascular outcomes. Methods Among the UK participants, we included 219,330 women aged 40 to 69 years who reported at least one live birth. The new incidence of diverse cardiovascular outcomes was compared according to GDM history by multivariable Cox proportional hazard models. In addition, causal mediation analysis was performed to examine the contribution of well-known risk factors to observed risk. Results After enrollment, 13,094 women (6.0%) developed new overall cardiovascular outcomes. Women with GDM history had an increased risk for overall cardiovascular outcomes [adjusted HR (aHR) 1.36 (95% CI 1.18–1.55)], including coronary artery disease [aHR 1.31 (1.08–1.59)], myocardial infarction [aHR 1.65 (1.27–2.15)], ischemic stroke [aHR 1.68 (1.18–2.39)], peripheral artery disease [aHR 1.69 (1.14–2.51)], heart failure [aHR 1.41 (1.06–1.87)], mitral regurgitation [aHR 2.25 (1.51–3.34)], and atrial fibrillation/flutter [aHR 1.47 (1.18–1.84)], after adjustment for age, race, BMI, smoking, early menopause, hysterectomy, prevalent disease, and medication. In mediation analysis, overt diabetes explained 23%, hypertension explained 11%, and dyslipidemia explained 10% of the association between GDM and overall cardiovascular outcome. Conclusions GDM was associated with more diverse cardiovascular outcomes than previously considered, and conventional risk factors such as diabetes, hypertension, and dyslipidemia partially contributed to this relationship.

Abstract Clinical guidelines recommend several risk factors to identify women in early pregnancy at high risk of developing pregnancy-associated hypertension. However, these variables result in low predictive accuracy. Here, we developed a prediction model for pregnancy-associated hypertension using graph-based semi-supervised learning. This is a secondary analysis of a prospective study of healthy pregnant women. To develop the prediction model, we compared the prediction performances across five machine learning methods (semi-supervised learning with both labeled and unlabeled data, semi-supervised learning with labeled data only, logistic regression, support vector machine, and random forest) using three different variable sets: [a] variables from clinical guidelines, [b] selected important variables from the feature selection, and [c] all routine variables. Additionally, the proposed prediction model was compared with placental growth factor, a predictive biomarker for pregnancy-associated hypertension. The study population consisted of 1404 women, including 1347 women with complete follow-up (labeled data) and 57 women with incomplete follow-up (unlabeled data). Among the 1347 with complete follow-up, 2.4% (33/1347) developed pregnancy-associated HTN. Graph-based semi-supervised learning using top 11 variables achieved the best average prediction performance (mean area under the curve (AUC) of 0.89 in training set and 0.81 in test set), with higher sensitivity (72.7% vs 45.5% in test set) and similar specificity (80.0% vs 80.5% in test set) compared to risk factors from clinical guidelines. In addition, our proposed model with graph-based SSL had a higher performance than that of placental growth factor for total study population (AUC, 0.71 vs. 0.80, p

Abstract Background Brain volume has been widely studied in the neuroimaging field, since it is an important and heritable trait associated with brain development, aging and various neurological and psychiatric disorders. Genome-wide association studies (GWAS) have successfully identified numerous associations between genetic variants such as single nucleotide polymorphisms and complex traits like brain volume. However, it is unclear how these genetic variations influence regional gene expression levels, which may subsequently lead to phenotypic changes. S-PrediXcan is a tissue-specific transcriptomic data analysis method that can be applied to bridge this gap. In this work, we perform an S-PrediXcan analysis on GWAS summary data from two large imaging genetics initiatives, the UK Biobank and Enhancing Neuroimaging Genetics through Meta Analysis, to identify tissue-specific transcriptomic effects on two closely related brain volume measures: total brain volume (TBV) and intracranial volume (ICV). Results As a result of the analysis, we identified 10 genes that are highly associated with both TBV and ICV. Nine out of 10 genes were found to be associated with TBV in another study using a different gene-based association analysis. Moreover, most of our discovered genes were also found to be correlated with multiple cognitive and behavioral traits. Further analyses revealed the protein–protein interactions, associated molecular pathways and biological functions that offer insight into how these genes function and interact with others. Conclusions These results confirm that S-PrediXcan can identify genes with tissue-specific transcriptomic effects on complex traits. The analysis also suggested novel genes whose expression levels are related to brain volumetric traits. This provides important insights into the genetic mechanisms of the human brain.

Abstract Background Few studies have examined associations between genetic risk for type 2 diabetes (T2D), lifestyle, clinical risk factors, and cardiovascular disease (CVD). We aimed to investigate the association of and potential interactions among genetic risk for T2D, lifestyle behavior, and metabolic risk factors with CVD. Methods A total of 345,217 unrelated participants of white British descent were included in analyses. Genetic risk for T2D was estimated as a genome-wide polygenic risk score constructed from > 6 million genetic variants. A favorable lifestyle was defined in terms of four modifiable lifestyle components, and metabolic health status was determined according to the presence of metabolic syndrome components. Results During a median follow-up of 8.9 years, 21,865 CVD cases (6.3%) were identified. Compared with the low genetic risk group, participants at high genetic risk for T2D had higher rates of overall CVD events, CVD subtypes (coronary artery disease, peripheral artery disease, heart failure, and atrial fibrillation/flutter), and CVD mortality. Individuals at very high genetic risk for T2D had a 35% higher risk of CVD than those with low genetic risk (HR 1.35 [95% CI 1.19 to 1.53]). A significant gradient of increased CVD risk was observed across genetic risk, lifestyle, and metabolic health status (P for trend > 0.001). Those with favorable lifestyle and metabolically healthy status had significantly reduced risk of CVD events regardless of T2D genetic risk. This risk reduction was more apparent in young participants (≤ 50 years). Conclusions Genetic risk for T2D was associated with increased risks of overall CVD, various CVD subtypes, and fatal CVD. Engaging in a healthy lifestyle and maintaining metabolic health may reduce subsequent risk of CVD regardless of genetic risk for T2D.

Abstract The expanding use of the phenome-wide association study (PheWAS) faces challenges in the context of using International Classification of Diseases billing codes for phenotype definition, imbalanced study population ethnicity, and constrained application of the results in research. We performed a PheWAS utilizing 136 deep phenotypes corroborated by comprehensive health check-ups in a Korean population, along with trans-ethnic comparisons through using the UK Biobank and Biobank Japan Project. Meta-analysis with Korean and Japanese population was done. The PheWAS associated 65 phenotypes with 14,101 significant variants (P

Background Cardiometabolic diseases are highly comorbid, but their relationship with female‐specific or overwhelmingly female‐predominant health conditions (breast cancer, endometriosis, pregnancy complications) is understudied. This study aimed to estimate the cross‐trait genetic overlap and influence of genetic burden of cardiometabolic traits on health conditions unique to women. Methods and Results Using electronic health record data from 71 008 ancestrally diverse women, we examined relationships between 23 obstetrical/gynecological conditions and 4 cardiometabolic phenotypes (body mass index, coronary artery disease, type 2 diabetes, and hypertension) by performing 4 analyses: (1) cross‐trait genetic correlation analyses to compare genetic architecture, (2) polygenic risk score–based association tests to characterize shared genetic effects on disease risk, (3) Mendelian randomization for significant associations to assess cross‐trait causal relationships, and (4) chronology analyses to visualize the timeline of events unique to groups of women with high and low genetic burden for cardiometabolic traits and highlight the disease prevalence in risk groups by age. We observed 27 significant associations between cardiometabolic polygenic scores and obstetrical/gynecological conditions (body mass index and endometrial cancer, body mass index and polycystic ovarian syndrome, type 2 diabetes and gestational diabetes, type 2 diabetes and polycystic ovarian syndrome). Mendelian randomization analysis provided additional evidence of independent causal effects. We also identified an inverse association between coronary artery disease and breast cancer. High cardiometabolic polygenic scores were associated with early development of polycystic ovarian syndrome and gestational hypertension. Conclusions We conclude that polygenic susceptibility to cardiometabolic traits is associated with elevated risk of certain female‐specific health conditions.

Abstract Background Various epigenetic factors are responsible for the non-genetic regulation on gene expression. The epigenetically dysregulated oncogenes or tumor suppressors by miRNA and/or DNA methylation are often observed in cancer cells. Each of these epigenetic regulators has been studied well in cancer progressions; however, their mutual regulatory relationship in cancer still remains unclear. In this study, we propose an integrative framework to systematically investigate epigenetic interactions between miRNA and methylation at the alternatively spliced mRNA level in bladder cancer. Each of these epigenetic regulators has been studied well in cancer progressions; however, their mutual regulatory relationship in cancer still remains unclear. Results The integrative analyses yielded 136 significant combinations (methylation, miRNA and isoform). Further, overall survival analysis on the 136 combinations based on methylation and miRNA, high and low expression groups resulted in 13 combinations associated with survival. Additionally, different interaction patterns were examined. Conclusions Our study provides a higher resolution of molecular insight into the crosstalk between two epigenetic factors, DNA methylation and miRNA. Given the importance of epigenetic interactions and alternative splicing in cancer, it is timely to identify and understand the underlying mechanisms based on epigenetic markers and their interactions in cancer, leading to alternative splicing with primary functional impact.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

BackgroundPrevious studies primarily targeted the ability of polygenic risk scores (PRSs) to predict a specific disease, and only a few studies have investigated the association between genetic risk scores and cardiovascular (CV) mortality. We assessed PRSs for coronary artery disease (CAD) and type 2 diabetes (T2DM) as the predictive factors for CV mortality, independent of traditional risk factors, and further investigated the additive effect between lifestyle behavior and PRS on CV mortality.MethodsWe used genetic and phenotypic data from UK Biobank participants aged 40–69 years at baseline, collected with standardized procedures. Genome-wide PRSs were constructed using >6 million genetic variants. Cox proportional hazard models were used to analyze the relationship between PRS and CV mortality with stratification by age, sex, disease status, and lifestyle behavior.ResultsOf 377,909 UK Biobank participants having European ancestry, 3,210 (0.8%) died due to CV disease during a median follow-up of 8.9 years. CV mortality risk was significantly associated with CAD PRS [low vs. very high genetic risk groups, CAD PRS hazard ratio (HR) 2.61 (2.02–3.36)] and T2DM PRS [HR 2.08 (1.58–2.73)], respectively. These relationships remained significant even after an adjustment for a comprehensive range of demographic and clinical factors. In the very high genetic risk group, adherence to an unfavorable lifestyle was further associated with a substantially increased risk of CV mortality [favorable vs. unfavorable lifestyle with very high genetic risk for CAD PRS, HR 8.31 (5.12–13.49); T2DM PRS, HR 5.84 (3.39–10.04)]. Across all genetic risk groups, 32.1% of CV mortality was attributable to lifestyle behavior [population attributable fraction (PAF) 32.1% (95% CI 28.8–35.3%)] and 14.1% was attributable to smoking [PAF 14.1% (95% CI 12.4–15.7%)]. There was no evidence of significant interaction between PRSs and age, sex, or lifestyle behavior in predicting the risk of CV mortality.ConclusionPRSs for CAD or T2DM and lifestyle behaviors are the independent predictive factors for future CV mortality in the white, middle-aged population. PRS-based risk assessment could be useful to identify the individuals who need intensive behavioral or therapeutic interventions to reduce the risk of CV mortality.

Abstract Background Introducing deep learning approach to medical images has rendered a large amount of un-decoded information into usage in clinical research. But mostly, it has been focusing on the performance of the prediction modeling for disease-related entity, but not on the clinical implication of the feature itself. Here we analyzed liver imaging features of abdominal CT images collected from 2019 patients with stage I – III colorectal cancer (CRC) using convolutional neural network (CNN) to elucidate its clinical implication in oncological perspectives. Results CNN generated imaging features from the liver parenchyma. Dimension reduction was done for the features by principal component analysis. We designed multiple prediction models for 5-year metachronous liver metastasis (5YLM) using combinations of clinical variables (age, sex, T stage, N stage) and top principal components (PCs), with logistic regression classification. The model using “1st PC (PC1) + clinical information” had the highest performance (mean AUC = 0.747) to predict 5YLM, compared to the model with clinical features alone (mean AUC = 0.709). The PC1 was independently associated with 5YLM in multivariate analysis (beta = − 3.831, P

Abstract The coronavirus disease 2019 (COVID-19) pandemic has had a significant impact on population health and wellbeing. Biomedical informatics is central to COVID-19 research efforts and for the delivery of healthcare for COVID-19 patients. Critical to this effort is the participation of informaticians who typically work on other basic science or clinical problems. The goal of this editorial is to highlight some examples of COVID-19 research areas that could benefit from informatics expertise. Each research idea summarizes the COVID-19 application area, followed by an informatics methodology, approach, or technology that could make a contribution. It is our hope that this piece will motivate and make it easy for some informaticians to adopt COVID-19 research projects.

Alzheimer's disease (AD) is the leading cause of dementia; however, men and women face differential AD prevalence, presentation, and progression risks. Characterizing metabolomic profiles during AD progression is fundamental to understand the metabolic disruptions and the biological pathways involved. However, outstanding questions remain of whether peripheral metabolic changes occur equally in men and women with AD. Here, we evaluated differential effects of metabolomic and brain volume associations between sexes. We used three cohorts from the Alzheimer's Disease Neuroimaging Initiative (ADNI), evaluated 1,368 participants, two metabolomic platforms with 380 metabolites in total, and six brain segment volumes. Using dimension reduction techniques, we took advantage of the correlation structure of the brain volume phenotypes and the metabolite concentration values to reduce the number of tests while aggregating relevant biological structures. Using WGCNA, we aggregated modules of highly co-expressed metabolites. On the other hand, we used partial least squares regression-discriminant analysis (PLS-DA) to extract components of brain volumes that maximally co-vary with AD diagnosis as phenotypes. We tested for differences in effect sizes between sexes in the association between single metabolite and metabolite modules with the brain volume components. We found five metabolite modules and 125 single metabolites with significant differences between sexes. These results highlight a differential lipid disruption in AD progression between sexes. Men showed a greater negative association of phosphatidylcholines and sphingomyelins and a positive association of VLDL and large LDL with AD progression. In contrast, women showed a positive association of triglycerides in VLDL and small and medium LDL with AD progression. Explicitly identifying sex differences in metabolomics during AD progression can highlight particular metabolic disruptions in each sex. Our research study and strategy can lead to better-tailored studies and better-suited treatments that take sex differences into account.

BackgroundPreoperative chemoradiotherapy (CRT) is a standard treatment for locally advanced rectal cancer (LARC). However, individual responses to preoperative CRT vary from patient to patient. The aim of this study is to develop a scoring system for the response of preoperative CRT in LARC using blood features derived from machine learning.MethodsPatients who underwent total mesorectal excision after preoperative CRT were included in this study. The performance of machine learning models using blood features before CRT (pre-CRT) and from 1 to 2 weeks after CRT (early-CRT) was evaluated. Based on the best model, important features were selected. The scoring system was developed from the selected model and features. The performance of the new scoring system was compared with those of systemic inflammatory indicators: neutrophil-to-lymphocyte ratio, platelet-to-lymphocyte ratio, lymphocyte-to-monocyte ratio, and the prognostic nutritional index.ResultsThe models using early-CRT blood features had better performances than those using pre-CRT blood features. Based on the ridge regression model, which showed the best performance among the machine learning models (AUROC 0.6322 and AUPRC 0.5965), a novel scoring system for the response of preoperative CRT, named Response Prediction Score (RPS), was developed. The RPS system showed higher predictive power (AUROC 0.6747) than single blood features and systemic inflammatory indicators and stratified the tumor regression grade and overall downstaging clearly.ConclusionWe discovered that we can more accurately predict CRT response by using early-treatment blood data. With larger data, we can develop a more accurate and reliable indicator that can be used in real daily practices. In the future, we urge the collection of early-treatment blood data and pre-treatment blood data.

Abstract Background Endometrial cancer (EMCA) is the fifth most common cancer among women in the world. Identification of potentially pathogenic germline variants from individuals with EMCA will help characterize genetic features that underlie the disease and potentially predispose individuals to its pathogenesis. Methods The Geisinger Health System’s (GHS) DiscovEHR cohort includes exome sequencing on over 50,000 consenting patients, 297 of whom have evidence of an EMCA diagnosis in their electronic health record. Here, rare variants were annotated as potentially pathogenic. Results Eight genes were identified as having increased burden in the EMCA cohort relative to the non-cancer control cohort. None of the eight genes had an increased burden in the other hormone related cancer cohort from GHS, suggesting they can help characterize the underlying genetic variation that gives rise to EMCA. Comparing GHS to the cancer genome atlas (TCGA) EMCA germline data illustrated 34 genes with potentially pathogenic variation and eight unique potentially pathogenic variants that were present in both studies. Thus, similar germline variation among genes can be observed in unique EMCA cohorts and could help prioritize genes to investigate for future work. Conclusion In summary, this systematic characterization of potentially pathogenic germline variants describes the genetic underpinnings of EMCA through the use of data from a single hospital system.

Abstract Background At least 90% of human genes are alternatively spliced. Alternative splicing has an important function regulating gene expression and miss-splicing can contribute to risk for human diseases, including Alzheimer’s disease (AD). Methods We developed a splicing decision model as a molecular mechanism to identify functional exon skipping events and genetic variation affecting alternative splicing on a genome-wide scale by integrating genomics, transcriptomics, and neuroimaging data in a systems biology approach. In this study, we analyzed RNA-Seq data of hippocampus brain tissue from Alzheimer’s disease (AD; n = 24) and cognitively normal elderly controls (CN; n = 50) and identified three exon skipping events in two genes (RELN and NOS1) as significantly associated with AD (corrected p-value 1.5). Next, we identified single-nucleotide polymorphisms (SNPs) affecting exon skipping events using the splicing decision model and then performed an association analysis of SNPs potentially affecting three exon skipping events with a global cortical measure of amyloid-β deposition measured by [18F] Florbetapir position emission tomography (PET) scan as an AD-related quantitative phenotype. A whole-brain voxel-based analysis was also performed. Results Two exons in RELN and one exon in NOS1 showed significantly lower expression levels in the AD participants compared to CN participants, suggesting that the exons tend to be skipped more in AD. We also showed the loss of the core protein structure due to the skipped exons using the protein 3D structure analysis. The targeted SNP-based association analysis identified one intronic SNP (rs362771) adjacent to the skipped exon 24 in RELN as significantly associated with cortical amyloid-β levels (corrected p-value

Abstract Background Alzheimer’s disease (AD) is one of the most common neurodegenerative diseases that causes problems related to brain function. To some extent it is understood on a molecular level how AD arises, however there are a lack of biomarkers that can be used for early diagnosis. Two popular methods to identify AD-related biomarkers use genetics and neuroimaging. Genes and neuroimaging phenotypes have provided some insights as to the potential for AD biomarkers. While the field of imaging-genomics has identified genetic features associated with structural and functional neuroimaging phenotypes, it remains unclear how variants that affect splicing could be important for understanding the genetic etiology of AD. Methods In this study, rare variants (minor allele frequency

Abstract Background Large-scale collaborative precision medicine initiatives (e.g., The Cancer Genome Atlas (TCGA)) are yielding rich multi-omics data. Integrative analyses of the resulting multi-omics data, such as somatic mutation, copy number alteration (CNA), DNA methylation, miRNA, gene expression, and protein expression, offer tantalizing possibilities for realizing the promise and potential of precision medicine in cancer prevention, diagnosis, and treatment by substantially improving our understanding of underlying mechanisms as well as the discovery of novel biomarkers for different types of cancers. However, such analyses present a number of challenges, including heterogeneity, and high-dimensionality of omics data. Methods We propose a novel framework for multi-omics data integration using multi-view feature selection. We introduce a novel multi-view feature selection algorithm, MRMR-mv, an adaptation of the well-known Min-Redundancy and Maximum-Relevance (MRMR) single-view feature selection algorithm to the multi-view setting. Results We report results of experiments using an ovarian cancer multi-omics dataset derived from the TCGA database on the task of predicting ovarian cancer survival. Our results suggest that multi-view models outperform both view-specific models (i.e., models trained and tested using a single type of omics data) and models based on two baseline data fusion methods. Conclusions Our results demonstrate the potential of multi-view feature selection in integrative analyses and predictive modeling from multi-omics data.

Abstract Background The Cancer Genome Atlas (TCGA) project is a public resource that provides transcriptomic, DNA sequence, methylation, and clinical data for 33 cancer types. Transforming the large size and high complexity of TCGA cancer genome data into integrated knowledge can be useful to promote cancer research. Alternative splicing (AS) is a key regulatory mechanism of genes in human cancer development and in the interaction with epigenetic factors. Therefore, AS-guided integration of existing TCGA data sets will make it easier to gain insight into the genetic architecture of cancer risk and related outcomes. There are already existing tools analyzing and visualizing alternative mRNA splicing patterns for large-scale RNA-seq experiments. However, these existing web-based tools are limited to the analysis of individual TCGA data sets at a time, such as only transcriptomic information. Results We implemented CAS-viewer (integrative analysis of Cancer genome data based on Alternative Splicing), a web-based tool leveraging multi-cancer omics data from TCGA. It illustrates alternative mRNA splicing patterns along with methylation, miRNAs, and SNPs, and then provides an analysis tool to link differential transcript expression ratio to methylation, miRNA, and splicing regulatory elements for 33 cancer types. Moreover, one can analyze AS patterns with clinical data to identify potential transcripts associated with different survival outcome for each cancer. Conclusions CAS-viewer is a web-based application for transcript isoform-driven integration of multi-omics data in multiple cancer types and will aid in the visualization and possible discovery of biomarkers for cancer by integrating multi-omics data from TCGA.

Abstract Background Machine learning methods have gained popularity and practicality in identifying linear and non-linear effects of variants associated with complex disease/traits. Detection of epistatic interactions still remains a challenge due to the large number of features and relatively small sample size as input, thus leading to the so-called “short fat data” problem. The efficiency of machine learning methods can be increased by limiting the number of input features. Thus, it is very important to perform variable selection before searching for epistasis. Many methods have been evaluated and proposed to perform feature selection, but no single method works best in all scenarios. We demonstrate this by conducting two separate simulation analyses to evaluate the proposed collective feature selection approach. Results Through our simulation study we propose a collective feature selection approach to select features that are in the “union” of the best performing methods. We explored various parametric, non-parametric, and data mining approaches to perform feature selection. We choose our top performing methods to select the union of the resulting variables based on a user-defined percentage of variants selected from each method to take to downstream analysis. Our simulation analysis shows that non-parametric data mining approaches, such as MDR, may work best under one simulation criteria for the high effect size (penetrance) datasets, while non-parametric methods designed for feature selection, such as Ranger and Gradient boosting, work best under other simulation criteria. Thus, using a collective approach proves to be more beneficial for selecting variables with epistatic effects also in low effect size datasets and different genetic architectures. Following this, we applied our proposed collective feature selection approach to select the top 1% of variables to identify potential interacting variables associated with Body Mass Index (BMI) in ~ 44,000 samples obtained from Geisinger’s MyCode Community Health Initiative (on behalf of DiscovEHR collaboration). Conclusions In this study, we were able to show that selecting variables using a collective feature selection approach could help in selecting true positive epistatic variables more frequently than applying any single method for feature selection via simulation studies. We were able to demonstrate the effectiveness of collective feature selection along with a comparison of many methods in our simulation analysis. We also applied our method to identify non-linear networks associated with obesity.

Centralized infrastructure to support analyses involving complexity beyond genome-wide association studies is broadly needed. Here, Ritchie and colleagues develop PLATO, a software tool to process and integrate various methods for this task.

The use of tissue adhesives for the closure of wounds is of growing interest for surgery and trauma management. Here, the authors develop an adhesive that is biocompatible, enables tissue adhesion and also permits real-time imaging due to the presence of contrast agents for multiple modalities.

Abstract Background Aspirin Exacerbated Respiratory Disease (AERD) is a chronic medical condition that encompasses asthma, nasal polyposis, and hypersensitivity to aspirin and other non-steroidal anti-inflammatory drugs. Several previous studies have shown that part of the genetic effects of the disease may be induced by the interaction of multiple genetic variants. However, heavy computational cost as well as the complexity of the underlying biological mechanism has prevented a thorough investigation of epistatic interactions and thus most previous studies have typically considered only a small number of genetic variants at a time. Methods In this study, we propose a gene network based analysis framework to identify genetic risk factors from a genome-wide association study dataset. We first derive multiple single nucleotide polymorphisms (SNP)-based epistasis networks that consider marginal and epistatic effects by using different information theoretic measures. Each SNP epistasis network is converted into a gene-gene interaction network, and the resulting gene networks are combined as one for downstream analysis. The integrated network is validated on existing knowledgebase of DisGeNET for known gene-disease associations and GeneMANIA for biological function prediction. Results We demonstrated our proposed method on a Korean GWAS dataset, which has genotype information of 440,094 SNPs for 188 cases and 247 controls. The topological properties of the generated networks are examined for scale-freeness, and we further performed various statistical analyses in the Allergy and Asthma Portal (AAP) using the selected genes from our integrated network. Conclusions Our result reveals that there are several gene modules in the network that are of biological significance and have evidence for controlling susceptibility and being related to the treatment of AERD.

Abstract Background One of the fundamental challenges in cancer is to detect the regulators of gene expression changes during cancer progression. Through transcriptional silencing of critical cancer-related genes, epigenetic change such as DNA methylation plays a crucial role in cancer. In addition, miRNA, another major component of epigenome, is also a regulator at the post-transcriptional levels that modulate transcriptome changes. However, a mechanistic role of synergistic interactions between DNA methylation and miRNA as epigenetic regulators on transcriptomic changes and its association with clinical outcomes such as survival have remained largely unexplored in cancer. Methods In this study, we propose an integrative framework to identify epigenetic interactions between methylation and miRNA associated with transcriptomic changes. To test the utility of the proposed framework, the bladder cancer data set, including DNA methylation, miRNA expression, and gene expression data, from The Cancer Genome Atlas (TCGA) was analyzed for this study. Results First, we found 120 genes associated with interactions between the two epigenomic components. Then, 11 significant epigenetic interactions between miRNA and methylation, which target E2F3, CCND1, UTP6, CDADC1, SLC35E3, METRNL, TPCN2, NACC2, VGLL4, and PTEN, were found to be associated with survival. To this end, exploration of TCGA bladder cancer data identified epigenetic interactions that are associated with survival as potential prognostic markers in bladder cancer. Conclusions Given the importance and prevalence of these interactions of epigenetic events in bladder cancer it is timely to understand further how different epigenetic components interact and influence each other.

Abstract Background The APOE ε4 allele is the most significant common genetic risk factor for late-onset Alzheimer’s disease (LOAD). The region surrounding APOE on chromosome 19 has also shown consistent association with LOAD. However, no common variants in the region remain significant after adjusting for APOE genotype. We report a rare variant association analysis of genes in the vicinity of APOE with cerebrospinal fluid (CSF) and neuroimaging biomarkers of LOAD. Methods Whole genome sequencing (WGS) was performed on 817 blood DNA samples from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Sequence data from 757 non-Hispanic Caucasian participants was used in the present analysis. We extracted all rare variants (MAF (minor allele frequency)

Abstract Background Breast cancer is a complex disease in which different genomic patterns exists depending on different subtypes. Recent researches present that multiple subtypes of breast cancer occur at different rates, and play a crucial role in planning treatment. To better understand underlying biological mechanisms on breast cancer subtypes, investigating the specific gene regulatory system via different subtypes is desirable. Methods Gene expression, as an intermediate phenotype, is estimated based on methylation profiles to identify the impact of epigenomic features on transcriptomic changes in breast cancer. We propose a kernel weighted l1-regularized regression model to incorporate tumor subtype information and further reveal gene regulations affected by different breast cancer subtypes. For the proper control of subtype-specific estimation, samples from different breast cancer subtype are learned at different rate based on target estimates. Kolmogorov Smirnov test is conducted to determine learning rate of each sample from different subtype. Results It is observed that genes that might be sensitive to breast cancer subtype show prediction improvement when estimated using our proposed method. Comparing to a standard method, overall performance is also enhanced by incorporating tumor subtypes. In addition, we identified subtype-specific network structures based on the associations between gene expression and DNA methylation. Conclusions In this study, kernel weighted lasso model is proposed for identifying subtype-specific associations between gene expressions and DNA methylation profiles. Identification of subtype-specific gene expression associated with epigenomic changes might be helpful for better planning treatment and developing new therapies.

Abstract Background Rapid advancement of next generation sequencing technologies such as whole genome sequencing (WGS) has facilitated the search for genetic factors that influence disease risk in the field of human genetics. To identify rare variants associated with human diseases or traits, an efficient genome-wide binning approach is needed. In this study we developed a novel biological knowledge-based binning approach for rare-variant association analysis and then applied the approach to structural neuroimaging endophenotypes related to late-onset Alzheimer’s disease (LOAD). Methods For rare-variant analysis, we used the knowledge-driven binning approach implemented in Bin-KAT, an automated tool, that provides 1) binning/collapsing methods for multi-level variant aggregation with a flexible, biologically informed binning strategy and 2) an option of performing unified collapsing and statistical rare variant analyses in one tool. A total of 750 non-Hispanic Caucasian participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort who had both WGS data and magnetic resonance imaging (MRI) scans were used in this study. Mean bilateral cortical thickness of the entorhinal cortex extracted from MRI scans was used as an AD-related neuroimaging endophenotype. SKAT was used for a genome-wide gene- and region-based association analysis of rare variants (MAF (minor allele frequency)

Endometrial cancer is the fourth most commonly diagnosed cancer in women. Family history is a known risk factor for endometrial cancer. The incidence of endometrial cancer in a first-degree relative elevates the relative risk to range between 1.3 and 2.8. It is unclear to what extent or what other novel germline variants are at play in endometrial cancer. We aim to address this question by utilizing whole exome sequencing as a means to identify novel, rare variant associations between exonic regions and endometrial cancer. The MyCode community health initiative is an excellent resource for this study with germline whole exome data for 60,000 patients available in the first phase, and further 30,000 patients independently sequenced in the second phase as part of DiscovEHR study. We conducted exome-wide rare variant association using 472 cases and 4,110 controls in 60,000 patients (discovery cohort); and 261 cases and 1,531 controls from 30,000 patients (replication cohort). After binning rare germline variants into genes, case-control association tests performed using Optimal Unified Approach for Rare-Variant Association, SKAT-O. Seven genes, including RBM12, NDUFB6, ATP6V1A, RECK, SLC35E1, RFX3 (Bonferroni-corrected P < 0.05) and ATP8A1 (suggestive P < 10−5), and one long non-coding RNA, DLGAP4-AS1 (Bonferroni-corrected P < 0.05), were associated with endometrial cancer. Notably, RECK, and ATP8A1 were replicated from the replication cohort (suggestive threshold P < 0.05). Additionally, a pathway-based rare variant analysis, using pathogenic and likely pathogenic variants, identified two significant pathways, pyrimidine metabolism and protein processing in the endoplasmic reticulum (Bonferroni-corrected P < 0.05). In conclusion, our results using the single-source electronic health records (EHR) linked to genomic data highlights candidate genes and pathways associated with endometrial cancer and indicates rare variants involvement in endometrial cancer predisposition, which could help in personalized prognosis and also further our understanding of its genetic etiology.

As large amounts of heterogeneous biomedical data become available, numerous methods for integrating such datasets have been developed to extract complementary knowledge from multiple domains of sources. Recently, a deep learning approach has shown promising results in a variety of research areas. However, applying the deep learning approach requires expertise for constructing a deep architecture that can take multimodal longitudinal data. Thus, in this paper, a deep learning-based python package for data integration is developed. The python package deep learning-based multimodal longitudinal data integration framework (MildInt) provides the preconstructed deep learning architecture for a classification task. MildInt contains two learning phases: learning feature representation from each modality of data and training a classifier for the final decision. Adopting deep architecture in the first phase leads to learning more task-relevant feature representation than a linear model. In the second phase, linear regression classifier is used for detecting and investigating biomarkers from multimodal data. Thus, by combining the linear model and the deep learning model, higher accuracy and better interpretability can be achieved. We validated the performance of our package using simulation data and real data. For the real data, as a pilot study, we used clinical and multimodal neuroimaging datasets in Alzheimer’s disease to predict the disease progression. MildInt is capable of integrating multiple forms of numerical data including time series and non-time series data for extracting complementary features from the multimodal dataset.

Eukaryotic organisms have developed a variety of mechanisms to regulate translation post-transcriptionally, including but not limited to the use of miRNA silencing in many species. One method of post-transcriptional regulation is through miRNAs that bind to the 3' UTRs to regulate mRNA abundance and influence protein expression. Therefore, the diversity of mRNA 3' UTRs mediating miRNA binding sites influence miRNA-mediated regulation. Alternative polyadenylation, by shortening mRNA isoforms, increases the diversity of 3' UTRs; moreover, short mRNA isoforms elude miRNA-medicated repression. Because no current prediction methods for putative miRNA target sites consider whether or not 1) splicing-informed miRNA binding sites and/or 2) the use of 3' UTRs provide higher resolution or functionality, we sought to identify not only the genome-wide impact of using exons in mRNA 3' UTRs but also their functional connection to miRNA regulation and clinical outcomes in cancer. With a genome-wide expression of mRNA and miRNA quantified by 395 bladder cancer cases from The Cancer Genome Atlas (TCGA), we 1) demonstrate the diversity of 3' UTRs affecting miRNA efficiency and 2) identify a set of genes clinically associated with mRNA expression in bladder cancer. Knowledge of 3' UTR diversity will not only be a useful addition to current miRNA target prediction algorithms but also enhance the clinical utility of mRNA isoforms in the expression of mRNA in cancer. Thus, variability among cancer patient's variability in molecular signatures based on these exon usage events in 3' UTR along with miRNAs in bladder cancer may lead to better prognostic/treatment strategies for improved precision medicine.

Following publication of the original article [1], the authors reported that Fig. 1 was not correctly processed during the production process. The correct Fig. 1 is given below.

ObjectivesRare disease research requires a broad range of disease-related information for the discovery of causes of genetic disorders that are maladies caused by abnormalities in genes or chromosomes. A rarity in cases makes it difficult for researchers to elucidate definite inception. This knowledge base will be a major resource not only for clinicians, but also for the general public, who are unable to find consistent information on rare diseases in a single location.MethodsWe design a compact database schema for faster querying; its structure is optimized to store heterogeneous data sources. Then, clinicians at Seoul National University Hospital (SNUH) review and revise those resources. Additionally, we integrated other sources to capture genomic resources and clinical trials in detail on the Korean Rare Disease Knowledge base (KRDK).ResultsAs a result, we have developed a Web-based knowledge base, KRDK, suitable for study of Mendelian diseases that commonly occur among Koreans. This knowledge base is comprised of disease summary and review, causal gene list, laboratory and clinic directory, patient registry, and so on. Furthermore, database for analyzing and giving access to human biological information and the clinical trial management system are integrated on KRDK.ConclusionsWe expect that KRDK, the first rare disease knowledge base in Korea, may contribute to collaborative research and be a reliable reference for application to clinical trials. Additionally, this knowledge base is ready for querying of drug information so that visitors can search a list of rare diseases that is relative to specific drugs. Visitors can have access to KRDK via http://www.snubi.org/software/raredisease/.